x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 150 insertions, 0 deletions

diff --git a/drivers/hwmon/gxp-fan-ctrl.c b/drivers/hwmon/gxp-fan-ctrl.c
new file mode 100644
index 000000000..64f85d7e7
--- /dev/null
+++ b/drivers/hwmon/gxp-fan-ctrl.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2023 Hewlett-Packard Enterprise Development Company, L.P. */
+
+#include <linux/err.h>
+#include <linux/hwmon.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+struct gxp_fan_ctrl_drvdata {
+	void __iomem	*base;
+};
+
+static int gxp_pwm_write(struct device *dev, u32 attr, int channel, long val)
+{
+	struct gxp_fan_ctrl_drvdata *drvdata = dev_get_drvdata(dev);
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		if (val > 255 || val < 0)
+			return -EINVAL;
+		writeb(val, drvdata->base + channel);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int gxp_fan_ctrl_write(struct device *dev, enum hwmon_sensor_types type,
+			      u32 attr, int channel, long val)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return gxp_pwm_write(dev, attr, channel, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int gxp_pwm_read(struct device *dev, u32 attr, int channel, long *val)
+{
+	struct gxp_fan_ctrl_drvdata *drvdata = dev_get_drvdata(dev);
+
+	*val = readb(drvdata->base + channel);
+
+	return 0;
+}
+
+static int gxp_fan_ctrl_read(struct device *dev, enum hwmon_sensor_types type,
+			     u32 attr, int channel, long *val)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return gxp_pwm_read(dev, attr, channel, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t gxp_fan_ctrl_is_visible(const void *_data,
+				       enum hwmon_sensor_types type,
+				       u32 attr, int channel)
+{
+	umode_t mode = 0;
+
+	switch (type) {
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+			mode = 0644;
+			break;
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return mode;
+}
+
+static const struct hwmon_ops gxp_fan_ctrl_ops = {
+	.is_visible = gxp_fan_ctrl_is_visible,
+	.read = gxp_fan_ctrl_read,
+	.write = gxp_fan_ctrl_write,
+};
+
+static const struct hwmon_channel_info * const gxp_fan_ctrl_info[] = {
+	HWMON_CHANNEL_INFO(pwm,
+			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT),
+	NULL
+};
+
+static const struct hwmon_chip_info gxp_fan_ctrl_chip_info = {
+	.ops = &gxp_fan_ctrl_ops,
+	.info = gxp_fan_ctrl_info,
+
+};
+
+static int gxp_fan_ctrl_probe(struct platform_device *pdev)
+{
+	struct gxp_fan_ctrl_drvdata *drvdata;
+	struct device *dev = &pdev->dev;
+	struct device *hwmon_dev;
+
+	drvdata = devm_kzalloc(dev, sizeof(struct gxp_fan_ctrl_drvdata),
+			       GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
+	if (IS_ERR(drvdata->base))
+		return dev_err_probe(dev, PTR_ERR(drvdata->base),
+				     "failed to map base\n");
+
+	hwmon_dev = devm_hwmon_device_register_with_info(&pdev->dev,
+							 "hpe_gxp_fan_ctrl",
+							 drvdata,
+							 &gxp_fan_ctrl_chip_info,
+							 NULL);
+
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+static const struct of_device_id gxp_fan_ctrl_of_match[] = {
+	{ .compatible = "hpe,gxp-fan-ctrl", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, gxp_fan_ctrl_of_match);
+
+static struct platform_driver gxp_fan_ctrl_driver = {
+	.probe		= gxp_fan_ctrl_probe,
+	.driver = {
+		.name	= "gxp-fan-ctrl",
+		.of_match_table = gxp_fan_ctrl_of_match,
+	},
+};
+module_platform_driver(gxp_fan_ctrl_driver);
+
+MODULE_AUTHOR("Nick Hawkins <nick.hawkins@hpe.com>");
+MODULE_DESCRIPTION("HPE GXP fan controller");
+MODULE_LICENSE("GPL");